search

NUAA-AL / ALiPy

ALiPy: Active Learning in Python is an active learning python toolbox, which allows users to conveniently evaluate, compare and analyze the performance of active learning methods.
http://parnec.nuaa.edu.cn/huangsj/alipy/
BSD 3-Clause "New" or "Revised" License
867 stars 115 forks source link

regression #29

Open zt823793279 opened 4 years ago

zt823793279 commented 4 years ago

Hello, how can I use its regression task？ When I give the toolbox a regressive label, it always produces the following errors ValueError: Unknown label type: (array([339.731, 340.059, 340.404, ..., 421.542, 423.743, 423.307]),)

thomasjhuang commented 4 years ago

I think that the closest you can get to doing regression for traditionally classification based tasks is by binning the range of continuous values that you have into uniform size intervals, and have your model classify into bins. Refer to the response on this stackexchange answer https://datascience.stackexchange.com/a/32486

AndyWangSFU commented 3 years ago

This is a very good question...I have been looking for toolkits regarding "active regression", but apparently most active learning techniques are designed only for classification tasks.

If you spend a little time looking at the logic of uncertainty sampling, it calculates some prior probability based on "class labels". They are nominal data instead of continuous.

Yuxing0926 commented 1 year ago

So this package cannot be used in regression task?

tangypnuaa commented 1 year ago

Hi, ALiPy does not support regression tasks in this version. Sorry for the inconvenience.